Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -150.85 +/- 77.91
+      value: -57.21 +/- 110.10
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1670359651.8fba07fb14db.771.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a4f5649ead5425611e25b5ed2f03c04cbb0c1983d4c56fe6d5c2d54419cf10d
+size 1006197

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6423a7cec329cbd63e1e7c57e08876cf3d53b8f98a6852ac067ecea725e9c4a9
+oid sha256:22c6a2ee66a04c7a7faf6bb1a94f7cf59bd363baf1fa860acd583ab5e7432c11
 size 42689

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -150.8473649376169, "std_reward": 77.90788150689698, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-06T20:46:45.646552"}
+{"env_id": "LunarLander-v2", "mean_reward": -57.21169570921112, "std_reward": 110.10176293301704, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-06T21:13:53.305487"}